Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58657
    Prev
    Next
    INDEX
    Explanations

    analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cool
    -0.08
     Cool
    -0.08
     café
    -0.08
     Cyril
    -0.08
     Celsius
    -0.07
    Cool
    -0.07
    ético
    -0.07
    cool
    -0.07
     spying
    -0.07
     tính
    -0.07
    POSITIVE LOGITS
     él
    0.08
    (search
    0.08
    (element
    0.08
    _Element
    0.07
     els
    0.07
    _REV
    0.07
     Petro
    0.07
     purpos
    0.07
    (turn
    0.07
    (dom
    0.07
    Activations Density 0.007%

    No Known Activations